context-management-context-save

Use when working with context management context save

1.31x

Quality

31%

Does it follow best practices?

Impact

91%

1.31x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/context-management-context-save/SKILL.md

The canonical home for this skill is context-management-context-save in sickn33/agentic-awesome-skills

Quality

Content

42%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a verbose, concept-heavy overview whose code examples are scaffolding rather than runnable guidance, and whose lone cross-file reference is broken. It has decent section structure but does little to make Claude concretely effective at the task.

Suggestions

Trim the Role/Purpose, Overview, Advanced Integration, and Future Roadmap sections to a few lines; assume Claude already understands context engineering and keep only what is non-obvious.

Replace pseudocode with executable, copy-paste-ready examples — define or stub the helper functions (extract_project_metadata, semantic_compression, etc.) or reference real libraries with concrete imports.

Fix or remove the broken `resources/implementation-playbook.md` reference, and move the large JSON schema and per-database integration notes into actual reference files linked one level deep from SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is padded with buzzword-heavy abstraction ('An elite context engineering specialist focused on comprehensive, semantic, and dynamically adaptable context preservation') plus non-actional sections like 'Future Roadmap' and 'Advanced Integration Capabilities', fitting 'noticeably verbose; several unnecessary explanations or padded sections'.	2 / 5
Actionability	Real code blocks and a JSON schema are present, but every function calls undefined helpers (extract_project_metadata, semantic_compression, advanced_vector_compression), making the examples pseudocode rather than executable; this matches 'some concrete guidance but incomplete; pseudocode instead of executable code'.	3 / 5
Workflow Clarity	Two numbered workflows give a rough sequence but use no commands, no validation checkpoints, and no feedback loops; per the batch-operation cap, context capture without validation cannot exceed 3.	3 / 5
Progressive Disclosure	Section headers provide real structure, but content that belongs in separate files (code, schema, multi-database integration) is inlined and the single reference to resources/implementation-playbook.md is buried in the Instructions and points to a non-existent file, matching 'some structure; references present but not clearly signaled; content that should be separate is inline'.	3 / 5
	Total	11 / 20 Passed

Description

20%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is essentially a broken, tautological trigger clause with no statement of capability, leaving a user unable to tell what the skill actually does or when to invoke it. It fails on every dimension except a faint presence of trigger keywords.

Suggestions

Rewrite as a third-person capability statement plus an explicit trigger, e.g. 'Captures, serializes, and retrieves project context across sessions. Use when the user wants to save or restore conversation/project context, persist institutional knowledge, or resume long-running work.'

Replace the redundant phrase 'context management context save' with concrete, natural terms users would actually say (e.g. 'save context', 'context snapshot', 'resume session').

Add 2-3 specific actions (e.g. 'extract architectural decisions', 'serialize to JSON/markdown', 'store embeddings in a vector DB') so the 'what' is explicit and the skill is distinguishable from generic memory skills.

Dimension	Reasoning	Score
Specificity	The description "Use when working with context management context save" names no concrete actions whatsoever — it is a pure when-clause with no capability statement, matching the anchor 'Entirely vague; no concrete actions; pure abstract language'.	1 / 5
Completeness	Only a 'when' is present with no 'what' — the description never states what the skill does, matching the anchor 'only when is present without what'; it does not fall to 1 because an explicit trigger clause exists.	2 / 5
Trigger Term Quality	It contains a couple of recognizable keywords ("context", "save") but the phrase "context management context save" is redundant jargon no user would naturally say, so it sits between 'no natural keywords' (1) and 'some relevant keywords' (3).	2 / 5
Distinctiveness Conflict Risk	The garbled, circular trigger "context management context save" is vague and would overlap with many general context/memory skills, fitting 'very broad; high overlap risk' rather than the more specific anchor 3.	2 / 5
	Total	7 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/context-management-context-save/SKILL.md
Commit: 57c135b

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.